PixelVAE++: Improved PixelVAE with Discrete Prior

Abstract

Constructing powerful generative models for natural images is a challenging task. PixelCNN models capture details and local information in images very well but have limited receptive field. Variational autoencoders with a factorial decoder can capture global information easily, but they often fail to reconstruct details faithfully. PixelVAE combines the best features of the two models and constructs a generative model that is able to learn local and global structures. Here we introduce PixelVAE++, a VAE with three types of latent variables and a PixelCNN++ for the decoder. We introduce a novel architecture that reuses a part of the decoder as an encoder. We achieve the state of the art performance on binary data sets such as MNIST and Omniglot and achieve the state of the art performance on CIFAR-10 among latent variable models while keeping the latent variables informative.

References in corpus (27)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Prototypical Networks for Few-shot Learning
• WaveNet: A Generative Model for Raw Audio
• Categorical Reparameterization with Gumbel-Softmax
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Deep Visual Domain Adaptation: A Survey
• Conditional Image Generation with PixelCNN Decoders
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Pixel Recurrent Neural Networks
• NICE: Non-linear Independent Components Estimation
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• Density estimation using Real NVP
• SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
• MADE: Masked Autoencoder for Distribution Estimation
• One-shot Learning with Memory-Augmented Neural Networks
• Variational Recurrent Auto-Encoders
• Implicit Generation and Generalization in Energy-Based Models
• VAE with a VampPrior
• PixelSNAIL: An Improved Autoregressive Generative Model
• Discrete Variational Autoencoders
• Fixing a Broken ELBO
• Techniques for Learning Binary Stochastic Feedforward Neural Networks
• DVAE++: Discrete Variational Autoencoders with Overlapping Transformations
• DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors
• GumBolt: Extending Gumbel trick to Boltzmann priors

Cited by in corpus (10)

• NVAE: A Deep Hierarchical Variational Autoencoder
• Score-based Generative Modeling in Latent Space
• Densely connected normalizing flows
• From Ansätze to Z-gates: a NASA View of Quantum Computing
• Predictive Sampling with Forecasting Autoregressive Models
• Direct Evolutionary Optimization of Variational Autoencoders With Binary Latents
• The ELBO of Variational Autoencoders Converges to a Sum of Three Entropies
• A Quaternion-Valued Variational Autoencoder
• Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory
• RBM-Flow and D-Flow: Invertible Flows with Discrete Energy Base Spaces